The ability of the brain to generate complex spatiotemporal patterns with specific timings is essential for motor learning and temporal processing. An approach that can model this function, using the spontaneous activity of a random neural network (RNN), is associated with orbital instability. We propose a simple system that learns an arbitrary time series as the linear sum of stable trajectories produced by several small network modules. New finding in computer experiments is that the trajectories of the module outputs are orthogonal to each other. They created a dynamic orthogonal basis acquiring a high representational capacity, which enabled the system to learn the timing of extremely long intervals, such as tens of seconds for a millisecond computation unit, and also the complex time series of Lorenz attractors. This self-sustained system satisfies the stability and orthogonality requirements and thus provides a new neurocomputing framework and perspective for the neural mechanisms of motor learning.

People tend to expect mental capabilities in a robot based on anthropomorphism and often attribute the cause and responsibility for a failure in human-robot interactions to the robot. This study investigated the relationship between mind perception, a psychological scale of anthropomorphism, and attribution of the cause and responsibility in human-robot interactions. Participants played a repeated noncooperative game with a human, robot, or computer agent, where their monetary rewards depended on the outcome. They completed questionnaires on mind perception regarding the agent and whether the participant’s own or the agent’s decisions resulted in the unexpectedly small reward. We extracted two factors of Experience (capacity to sense and feel) and Agency (capacity to plan and act) from the mind perception scores. Then, correlation and structural equation modeling (SEM) approaches were used to analyze the data. The findings showed that mind perception influenced attribution processes differently for each agent type. In the human condition, decreased Agency score during the game led to greater causal attribution to the human agent, consequently also increasing the degree of responsibility attribution to the human agent. In the robot condition, the post-game Agency score decreased the degree of causal attribution to the robot, and the post-game Experience score increased the degree of responsibility to the robot. These relationships were not observed in the computer condition. The study highlights the importance of considering mind perception in designing appropriate causal and responsibility attribution in human-robot interactions and developing socially acceptable robots.

Understanding how the structural organization of neural networks influences their computational capabilities is of great interest to both machine learning and neuroscience communities. In our previous work, we introduced a novel learning system, called the reservoir of basal dynamics (reBASICS), which features a modular neural architecture (small-sized random neural networks) capable of reducing chaoticity of neural activity and of producing stable self-sustained limit cycle activities. The integration of these limit cycles is achieved by linear summation of their weights, and arbitrary time series are learned by modulating these weights. Despite its excellent learning performance, interpreting a modular structure of isolated small networks as a brain network has posed a significant challenge. Here, we investigate how local connectivity, a well-known characteristic of brain networks, contributes to reducing neural system chaoticity and generates self-sustained limit cycles based on empirical experiments. Moreover, we present the learning performance of the locally connected reBASICS in two tasks: a motor timing task and a learning task of the Lorenz time series. Although its performance was inferior to that of modular reBASICS, locally connected reBASICS could learn a time series of tens of seconds while the time constant of neural units was ten milliseconds. This work indicates that the locality of connectivity in neural networks may contribute to generation of stable self-sustained oscillations to learn arbitrary long-term time series, as well as the economy of wiring cost.

The integrated gradients (IG) method is widely used to evaluate the extent to which each input feature contributes to the classification using a deep learning model because it theoretically satisfies the desired properties to fairly attribute the contributions to the classification. However, this approach requires an appropriate baseline to do so. In this study, we propose a compensated IG method that does not require a baseline, which compensates the contributions calculated using the IG method at an arbitrary baseline by using an example of the Shapley sampling value. We prove that the proposed approach can compute the contributions to the classification results reliably if the processes of each input feature in a classifier are independent of one another and the parameterization of each process is identical, as in shared weights in convolutional neural networks. Using three datasets on electroencephalogram recordings, we experimentally demonstrate that the contributions obtained by the proposed compensated IG method are more reliable than those obtained using the original IG method and that its computational complexity is much lower than that of the Shapley sampling method.